© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 15244
    Prev
    Next
    INDEX
    Explanations

    references to the Office of Science or Office of Science-related research programs

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.91
     offices
    -0.72
     跳转至
    -0.68
    Clik
    -0.65
    abestanden
    -0.64
    Kanpo
    -0.64
     escritorio
    -0.63
    IntoConstraints
    -0.63
    CloseOperation
    -0.63
    ]")]
    -0.63
    POSITIVE LOGITS
     Office
    2.05
    Office
    1.60
     OFFICE
    0.99
    OFFICE
    0.80
     Oficina
    0.77
    Oficina
    0.53
    ḫ
    0.52
     criminal
    0.49
    setzung
    0.48
    ospels
    0.48
    Activations Density 0.008%

    No Known Activations